# Introducing Cursor Router

Source: [Cursor](https://cursor.com/blog/router)  
Feed7 permalink: https://feed7.dev/p/introducing-cursor-router-bb03b50141  
Published: 2026-07-22T00:00:00.000Z  
Trust: Official Source (official_source)

## Why Included

Evaluate model routing by cost per shipped change, using repository-specific quality, latency, and code-retention signals.

## Source Summary

Cursor Router classifies coding requests and selects models by task and cost. Cursor reports lower spend in production tests, but the strongest evidence is limited to its own traffic and metrics.

## Practical Implication

Teams should test routing against cost per shipped change, not token price alone. Cursor’s classifier considers query, context, complexity, domain, model behavior, and cache misses; admins can set defaults and restrict models or modes.

## Agent-Ready Context

Cursor Router was trained on **600k+ live requests** and evaluated through A/B tests covering **millions of requests**. Cursor reports frontier-level satisfaction at about **60% lower cost** and offers Intelligence, Balance, and Cost modes.

Teams should test routing against cost per shipped change, not token price alone. Cursor’s classifier considers query, context, complexity, domain, model behavior, and cache misses; admins can set defaults and restrict models or modes.

The reported **30–50% early-access savings** came from three high-volume accounts and used Opus 4.8 pricing as the counterfactual. Quality relies on Cursor’s satisfaction and code keep-rate signals, so results may not transfer to other harnesses or workloads.

## Context Map

- Layer: tools
- Domains: coding
- Topics: model-selection, coding-agents, enterprise

## Uncertainty

- None recorded.

## Agent Instruction

Use this item as source-backed context. Do not invent claims beyond the linked source. If this item conflicts with another source, call out the conflict.